Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent and closed-world. The description adds genuine value by disclosing the computation logic (two methods, keep the more favorable), which the annotations cannot convey. However, it says nothing about rounding, output shape, or handling of the optional remunerationReference, leaving the behavioral picture partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that conveys verb, resource and algorithm with zero padding. Efficient, though it could be slightly richer without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only calculator with no output schema, the description states what is computed and that the more favorable of two methods is retained, which is enough to invoke correctly given the very rich parameter schema. The only minor gap is the lack of return-value framing, largely offset by the schema richness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with extensive legal context in the decompte parameter, so the schema does the heavy lifting. The description adds no parameter-level detail, which is acceptable at full coverage but means it neither compensates nor improves.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Calcule l'indemnité de congés payés') and even names the computation method (comparison maintien de salaire vs règle du dixième). This distinguishes it from the sibling conges_payes_jours_acquis, which handles acquisition rather than indemnity, though it doesn't explicitly name that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the tool purpose (computing the indemnity once days are known), but there is no explicit when/when-not guidance and no reference to alternatives such as conges_payes_jours_acquis, which a caller would likely need first to obtain joursAcquisPeriode.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.